Part 1: PCA with penguins

penguin_pca <- penguins %>% 
  select(body_mass_g, ends_with("_mm")) %>%  # helper function for select
  drop_na() %>% # drop na obs from any column
  scale() %>% 
  prcomp()
  
penguin_pca$rotation # loadings are here for the PCs  
##                          PC1         PC2        PC3        PC4
## body_mass_g        0.5483502 0.084362920 -0.5966001 -0.5798821
## bill_length_mm     0.4552503 0.597031143  0.6443012 -0.1455231
## bill_depth_mm     -0.4003347 0.797766572 -0.4184272  0.1679860
## flipper_length_mm  0.5760133 0.002282201 -0.2320840  0.7837987
penguin_complete <- penguins %>% 
  drop_na(body_mass_g, ends_with("_mm"))

autoplot(penguin_pca,
         data = penguin_complete,
         colour = "species",
         loadings = TRUE,
         loadings.label = TRUE) +
  theme_minimal() #  can add ggplot functions to autoplot, can also change arrow size and other things. 
## Warning: `select_()` is deprecated as of dplyr 0.7.0.
## Please use `select()` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_warnings()` to see where this warning was generated.

# other ways to make pca biplots in r as well.

Part 2: ggplot2 customization & reading in different file types

read in a .xlsx file & do some wrangling

fish_noaa <- read_excel(here("data", "foss_landings.xlsx")) %>% 
  clean_names() %>% # default is to convert all col names to snake case
  mutate(across(where(is.character), tolower)) %>%  # for any char col use func `to_lower`
  mutate(nmfs_name = str_sub(nmfs_name, end = -4)) %>%  #  Here we are removing the last 4 characters from the col. 
  filter(confidentiality == "public")

# usually someone has already written a function you want to use.

Make a customized graph

fish_plot <- ggplot(data = fish_noaa, aes(x = year, y = pounds)) +
  geom_line(aes(color = nmfs_name), show.legend = FALSE) +
  theme_minimal()

fish_plot
## Warning: Removed 6 row(s) containing missing values (geom_path).

ggplotly(fish_plot)